AI ecosystem helps ETZ radiologists formulate the right diagnosis faster
Is the patient's bone broken?
Every day, the Tilburg radiologists assess approximately 100 X-rays in the Elisabeth-TweeSteden Hospital (ETZ) to answer that question.
To formulate the right diagnosis faster and more efficiently, they are now trial-testing AI applications.
The artificial intelligence application they're trying, is called BoneView.
“We are the first hospital to use this algorithm,” says radiologist Prof. Erik Ranschaert. Before it was put into use at the ETZ, Prof. Ranschaert and his colleagues tested the AI application on a selection of 600 recent X-rays. Then they had them analysed by BoneView.
The first test result of the BoneView analysis was positive. Prof. Ranschaert: “BoneView turned out to be able to find fractures that even the specialists could not see with the naked eye. In the test, BoneView ‘discovered’ previously undetected fractures.
Prof. Ranschaert: “A smart use of this technology, means that BoneView can prevent 360 to 370 missed fractures per year. That is a considerable number.”
Prof. Ranschaert make a strong case for the need for the expertise of the radiologist. BoneView cannot completely take over the assessment from the radiologist. “BoneView also missed 3 proven fractures in the test. Nonetheless, the overall results are positive and contributing to the bigger picture, so we will be testing BoneView on a larger scale from now on.” At this point, not only the radiologists are getting acquainted with BoneView, but also technologists, emergency physicians, surgeons, and orthopeadics.
The BoneView process
Each X-ray that is created, is automatically forwarded to a server that runs the algorithm. The software will analyse the pictures and advise whether there is a fracture, no fracture, or if there is doubt. In most assessment case, the algorithm confirms a fracture. In that case, the software places a fixed line on the picture illustrating the location of the fracture. If there is doubt, it will place a dotted link on what it thinks is a fracture.
"When in doubt, the specialist will double check whether or not there is a fracture at this location," explains Prof. Ranschaert.
“In any case, the radiologist always has to make the final report, which means every picture will have a final assessment by the doctor. As the trial progresses, radiologists, X-ray technologists, and all other doctors will gain more experience with the reliability of the algorithm.”
The algorithm works fast; BoneView analyses an exam in less than three minutes. By the time the specialist looks at the pictures, BoneView has already done the first analysis, saving the doctor some time or sharpening their attention on other elements.
Timing and outcome
The trial in the ETZ will run three months. Prof. Ranschaert emphasises once again that the AI application does not replace the specialists. “The main goal is to rule out fractures. BoneView offers the specialist an extra pair of eyes that works very precisely around the clock. It is meant to be a useful support for a job that requires a great deal from the doctor. The final assessment of the X-rays stays an important task of the specialist, who remains ultimately responsible. Patient safety is guaranteed in all respects.”
During the trial, graduates from Fontys Paramedische Hogeschool Eindhoven investigate the influence of AI on the work process of X-ray lab technicians. The 6 fourth-year students each investigate different elements. Their evaluations will be turned into the graduation project ‘Implementation of AI – pilot BoneView – in the Radiology department’.
The bigger AI scope at ETZ
BoneView is but one of the initiatives the ETZ initiated in the field of AI. The ETZ uses AI as an effective innovation that leads to quality improvement in healthcare. At the same time, AI must also contribute to affordable, sustainable care. That's why ETZ set up an ‘AI end user group ’. This group focuses on supporting healthcare providers who have an idea for an AI application, reviewing all proposed AI projects, building and recording knowledge and expertise in the field of AI, ensuring the requirements of an equipped AI infrastructure, knowledge management regarding AI within and outside the ETZ, inspiring employees and actively involving external partners.